AI Paper Atlas

Research map / Detection and segmentation / CNN features

Detecting Every Object From Events

Haitian Zhang, Chang Xu, Xinya Wang, Bingde Liu, Guang Hua, Lei Yu, Wen Tao Yang

TPAMI 2025 · Detection and segmentation › CNN features · approach: Spiking event-camera detection · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add disentangled objectness head (ablation)CA-RVT · Four Hour 1 Mpx, 5+2AUC (unknown classes): 17.77 -> 20.79Improved
add dual regressor head with potential samples (ablation)CA-RVT · Four Hour 1 Mpx, 5+2AUC (unknown classes): 17.77 -> 20.29Improved
add both heads (ablation)CA-RVT · Four Hour 1 Mpx, 5+2AUC (unknown classes): 17.77 -> 22.70Improved
add dual regressor head alone, measured on all classes (ablation)CA-RVT · Four Hour 1 Mpx, 5+2AUC (all classes): 34.88 -> 33.83Hurt
add positive-only branch alongside positive-negative branch (ablation)Disentangled head · Four Hour 1 Mpx, 5+2AR30 (unknown classes): 22.49 -> 26.00Improved
use positive-only branch alone instead of positive-negative (ablation)Objectness head · Four Hour 1 Mpx, 5+2AR10 (all classes): 41.38 -> 33.79Mixed
raise potential sample count from 0 to 35 (ablation)DEOE · Four Hour 1 Mpx, 5+2AUC (unknown classes): 20.25 -> 22.70Improved
raise potential sample count from 35 to 75 (ablation)DEOE · Four Hour 1 Mpx, 5+2AUC (unknown classes): 22.70 -> 19.62Hurt
use DEOE instead of CA-RVT baselineRVT · Four Hour 1 Mpx, 5+2AUC (unknown classes): 17.77 -> 22.70Improved
use DEOE instead of CA-RVT baselineRVT · Four Hour 1 Mpx, 4+3AUC (unknown classes): 8.83 -> 12.49Improved
use DEOE instead of CA-RVT_P in cross-dataset testRVT · DSEC-Detection (cross-dataset)AUC (unknown classes): 11.16 -> 15.07Improved
use DEOE instead of CA-RVT, inference timeRVT · Four Hour 1 Mpx, 5+2Inference time (ms): 6.19 -> 8.82Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy